INDEX

Explanations

words indicating an intermediate stage or state.

oai_token-act-pair · gemini-2.0-flash

Mid-level

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 فريبيس

-0.90

########.

-0.89

tvguidetime

-0.83

 صوتيه

-0.75

 للمعارف

-0.75

 propOrder

-0.69

GraphicsUnit

-0.69

 Theſe

-0.69

expandindo

-0.68

EndProject

-0.68

POSITIVE LOGITS

0.48

0.47

0.44

localctx

0.44

 perdere

0.40

bi

0.39

tom

0.38

as

0.38

feira

0.38

 chịu

0.37

Activations Density 1.450%

words indicating an intermediate stage or state.

Mid-level

No Known Activations